Suno Adds AI Video Generation for Its AI Music Tracks
AI music platform Suno now generates accompanying videos and images for its AI-created songs, pushing the company deeper into multimodal synthetic media and automated content creation.
AI music platform Suno now generates accompanying videos and images for its AI-created songs, pushing the company deeper into multimodal synthetic media and automated content creation.
Anthropic's upcoming IPO reveals that Amazon and Google together will control nearly 30% of the AI lab, cementing cloud giants' grip on frontier model development and the broader generative AI ecosystem.
AI-generated deepfake videos of Sam Altman and Meta's Alexandr Wang are circulating freely on Instagram, exposing how poorly major platforms police synthetic media of even their own tech elite.
A new method called Mem2Fair uses a 'Fair Memory' mechanism to dynamically control demographic bias in text-to-video generation at inference time, tackling one of synthetic media's most persistent problems without costly retraining.
A new research framework called Découpage brings directorial-level audio-visual control to long, multi-shot AI video generation, tackling one of the hardest challenges in synthetic media: coherent narrative across multiple shots.
Deepfake-enabled fraud has cost victims and organizations nearly $4 billion worldwide since 2020, highlighting the accelerating threat of AI-generated voice and video in financial scams, identity theft, and corporate deception.
New neuroscience research uses brain imaging to explain why AI-generated faces can appear "hyperreal" — sometimes more real than genuine human faces — revealing how our visual systems process synthetic media.
Jordan Belfort, the infamous 'Wolf of Wall Street,' has launched Tone, an AI voice startup aiming to bring his sales persuasion playbook to synthetic voice agents for businesses.
A new physics-inspired detection approach identifies fake faces by analyzing inconsistencies in color and brightness patterns, exploiting the way synthetic generators struggle to replicate real-world lighting physics.
Researchers built a dual-transformer architecture that flags AI-generated tweets with over 93 percent accuracy, offering a new line of defense against synthetic text flooding social platforms.
Researchers unveil a hybrid AI model combining spectral and deep-learning features to detect synthetic voice audio with 94% accuracy, offering a new defense against increasingly convincing voice-cloning attacks.
Weight-space programming treats neural network parameters as data that can be generated, edited, and reasoned about—letting one AI effectively write another AI's brain. Here's how hypernetworks and weight-space learning are reshaping model design.